Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129908
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and measurements related to astronomical observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    MF16, SS433, GRFs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     encantó
    -0.27
    DOCTYPE
    -0.24
     obligado
    -0.23
    locations
    -0.22
     calendriers
    -0.22
     llegamos
    -0.21
     later
    -0.20
     кислота
    -0.20
     điều
    -0.20
    等
    -0.20
    POSITIVE LOGITS
     ModelExpression
    0.71
    webElementXpaths
    0.69
    rungsseite
    0.67
    دانشنامهٔ
    0.66
    Microkernel
    0.66
     OMITBAD
    0.66
    GOTREF
    0.65
    الحياه
    0.65
     UnityEditor
    0.64
     ſei
    0.63
    Activations Density 0.067%

    No Known Activations